Synergistic learning of lung lobe segmentation and hierarchical multi-instance classification for automated severity assessment of COVID-19 in CT images.
Synergistic learning of lung lobe segmentation and hierarchical multi-instance classification for automated severity assessment of COVID-19 in CT images.
复制标题
DOI：
10.1016/j.patcog.2021.107828
复制
发表时间：
2021-05
影响因子：
8
通讯作者：
Shen D
中科院分区：
文献类型：
--
作者：
He K;Zhao W;Xie X;Ji W;Liu M;Tang Z;Shi Y;Shi F;Gao Y;Liu J;Zhang J;Shen D
了解2019冠状病毒病（COVID-19）的胸部CT成像将有助于早期发现感染并评估疾病进展。特别是，CT图像中COVID-19的自动严重程度评估在识别急需加强临床护理的病例方面发挥着至关重要的作用。然而，在CT图像中准确评估这种疾病的严重程度通常是具有挑战性的，因为肺部的感染区域可变，成像生物标志物相似，病例间差异大。为此，我们提出了一个协同学习框架，通过联合执行肺叶分割和多实例分类，在3D CT图像中自动评估COVID-19的严重程度。考虑到CT图像中只有少数感染区域与严重性评估相关，我们首先用包含一组2D图像块（每个块都从特定切片中裁剪）的袋子表示每个输入图像。然后开发多任务多实例深度网络（称为MUNet），以评估COVID-19患者的严重程度，并同时分割肺叶。我们的MUNet由一个补丁级编码器，一个用于肺叶分割的分割子网络和一个用于严重程度评估的分类子网络（具有独特的分层多实例学习策略）组成。在这里，由分段提供的上下文信息可以被隐式地用于提高严重性评估的性能。在由666张胸部CT图像组成的真实的COVID-19 CT图像数据集上进行了广泛的实验，结果表明，与几种最先进的方法相比，我们提出的方法是有效的。
Understanding chest CT imaging of the coronavirus disease 2019 (COVID-19) will help detect infections early and assess the disease progression. Especially, automated severity assessment of COVID-19 in CT images plays an essential role in identifying cases that are in great need of intensive clinical care. However, it is often challenging to accurately assess the severity of this disease in CT images, due to variable infection regions in the lungs, similar imaging biomarkers, and large inter-case variations. To this end, we propose a synergistic learning framework for automated severity assessment of COVID-19 in 3D CT images, by jointly performing lung lobe segmentation and multi-instance classification. Considering that only a few infection regions in a CT image are related to the severity assessment, we first represent each input image by a bag that contains a set of 2D image patches (with each cropped from a specific slice). A multi-task multi-instance deep network (called MUNet) is then developed to assess the severity of COVID-19 patients and also segment the lung lobe simultaneously. Our MUNet consists of a patch-level encoder, a segmentation sub-network for lung lobe segmentation, and a classification sub-network for severity assessment (with a unique hierarchical multi-instance learning strategy). Here, the context information provided by segmentation can be implicitly employed to improve the performance of severity assessment. Extensive experiments were performed on a real COVID-19 CT image dataset consisting of 666 chest CT images, with results suggesting the effectiveness of our proposed method compared to several state-of-the-art methods.
登录
查看更多内容
DOI：
10.1148/ryct.2020200075
发表时间：
2020-04-01
期刊：
RADIOLOGY-CARDIOTHORACIC IMAGING
影响因子：
--
作者：
Huang, Lu;Han, Rui;Xia, Liming
通讯作者：
Xia, Liming
影响因子：
10.9
作者：
Mohamed, Ashraf;Zacharaki, Evangelia I.;Davatzikos, Christos
通讯作者：
Davatzikos, Christos
DOI：
10.1109/tits.2021.3112458
发表时间：
2021-09-24
影响因子：
8.5
作者：
Song, Yongze;Wu, Peng;Karunaratne, Lalinda
通讯作者：
Karunaratne, Lalinda
影响因子：
10.9
作者：
Tong, Tong;Wolz, Robin;Rueckert, Daniel
通讯作者：
Rueckert, Daniel
DOI：
10.1016/s1473-3099(20)30243-7
发表时间：
2020-06-01
期刊：
The Lancet. Infectious diseases
影响因子：
--
作者：
Verity, Robert;Okell, Lucy C;Ferguson, Neil M
通讯作者：
Ferguson, Neil M